Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 867 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1069516 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1097096 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4845. Min Act: -0.0000

Data Index: 1018471 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4673. Min Act: -0.0000

Data Index: 998799 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4370. Min Act: -0.0000

Data Index: 701261 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4026. Min Act: -0.0000

Data Index: 947253 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.3836. Min Act: -0.0000

Data Index: 1017202 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.3920. Min Act: -0.0000

Data Index: 842489 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.3812. Min Act: -0.0000

Data Index: 246478 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.3549. Min Act: -0.0000

Data Index: 682358 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1042260 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.3731. Min Act: -0.0000

Data Index: 1135753 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.3468. Min Act: -0.0000

Data Index: 1211316 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.3557. Min Act: -0.0000

Data Index: 221070 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.3529. Min Act: -0.0000

Data Index: 634434 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.3584. Min Act: -0.0000

Data Index: 16486 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.3471. Min Act: -0.0000

Data Index: 714118 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.3579. Min Act: -0.0000

Data Index: 859085 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.3304. Min Act: -0.0000

Data Index: 670603 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.3309. Min Act: -0.0000

Data Index: 2895 (C4 (Web Text))

Max Activating Token Index: 657